This paper presents a quantitative approach to the study of surfaces using surface metrology and data science techniques. Asian lacquer types with various additives have a quantifiable impact on the topography of lacquered surfaces that may be used to detect lacquer type from non-contact measurements. To understand the unaged and aged characteristics, 15 different formulas of Asian lacquer were prepared using laccol, thitsi, and urushi with a range of oils, pigments, and resins were examined. The surfaces of the Asian lacquers test specimens were studied using confocal microscopy to acquire quantitative surface texture data, and data science methods of feature engineering and convolutional neural networks (CNN) were applied to analyze the numerical surface texture data, and assign lacquer specimens to the three lacquer types. Correct classification rates reached as high as 96%.